Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Sume API media URL rules: which URLs each endpoint accepts
Sume generation endpoints fetch public HTTPS media URLs. Trim, filter, frames, inspect, and Timeline take only your workspace's media.sume.com URLs.
Sume job types and concurrency: which calls take a slot
Each Sume endpoint's job type and slot use: every generation job, trims and Timeline included, takes a concurrency slot; frames and inspect don't.
Sume API endpoints list: routes, scopes, idempotency
An index of the Sume API's public routes by family: which need no key, which scope each needs, where Idempotency-Key applies, and the post on each.
Sume API output file formats: MP4, PNG, WebP, WAV, MP3
The file each Sume API endpoint returns: MP4 from Timeline and the editing tools, PNG, JPEG, or WebP images, WAV or MP3 audio, and JSON transcripts.
Seedance 2.5 API: 30-second clips, resolutions, references
Seedance 2.5 on Sume is seedance-2.5: 4–30 second clips at 480p, 720p, or 1080p. The documented limits, inputs, and billing for each Seedance id.
Sora API alternatives for video generation after the shutdown
The Sora API shut down on September 24, 2026. Compare Runway, Kling, fal, Replicate and Sume by models, audio, price unit, API shape and limits.
AWS Lambda webhook receiver for Sume: function URL and HMAC
Give Sume a Lambda function URL with auth type NONE, decode the event body, check the sume-v1 HMAC, and answer 204 inside the 10-second window.
Inngest wait for event: resume when a Sume video run ends
Start a Sume run in step.run, turn its webhook into an Inngest event with a transform, then step.waitForEvent on the run id with a 2h timeout.
OpenAI Responses API MCP tool: call Sume's hosted tools
Add Sume's hosted MCP server to the Responses API as an mcp tool, send your Sume key in headers, and approve paid tool calls before they run.
Claude API MCP connector with Sume: what works today
The Claude API MCP connector has no documented way to authenticate to Sume's hosted MCP today. Why, and what to use instead, like the Agent SDK.
Gemini CLI MCP server: add Sume's hosted MCP
Add Sume's hosted MCP server to Gemini CLI with httpUrl and an API-key header read from your environment, then allowlist and confirm its tools.
Windsurf MCP server: add Sume's hosted MCP in Devin Desktop
Windsurf is now Devin Desktop. Add Sume's hosted MCP server to the Devin Local agent or the legacy Cascade agent with an API-key header.
Cline MCP remote server: add Sume's hosted MCP
Add Sume's hosted MCP server to Cline as a remote server with type streamableHttp and an API-key header, and keep paid tools out of autoApprove.
Pydantic AI MCP server: give an agent Sume's hosted tools
Connect a Pydantic AI agent to Sume's hosted MCP server with MCPToolset and an API-key header, filter the tools, and hold paid calls for approval.
Google ADK MCP tools: connect McpToolset to Sume's server
Add Sume's hosted MCP server to a Google ADK agent with McpToolset, an API-key header, and tool_filter, and make paid tools ask for confirmation.
Mastra MCP client: connect an agent to Sume's hosted MCP
Connect a Mastra agent to Sume's hosted MCP server with MCPClient: an API-key header in requestInit, a tool allow-list, and approval for paid calls.
n8n MCP Client Tool with Sume: setup and the SSE caveat
n8n labels the MCP Client Tool field SSE Endpoint; Sume documents streamable HTTP. Set it up for Sume, test the connection, and gate paid calls.
Dify custom tool from OpenAPI: import the Sume API schema
Make a Dify custom tool from Sume's OpenAPI schema: trim it to three video operations, import it as a Swagger API tool, and keep the key secret.
Bubble API Connector: generate AI video with the Sume API
Set up Bubble's API Connector for Sume: the key in a private header, a manual response so setup costs nothing, and a backend poll of the job.
Gradio video generation app: Sume API key in a Space secret
Build a Gradio video generation app on the Sume API: the key stays in a Hugging Face Space secret, a generator polls the job, and gr.Video plays it.
Telegram bot to generate video: a Sume job, then sendVideo
A Telegram bot can turn /video into a Sume job, reply at once, then call sendVideo with the artifact URL when Sume's signed webhook arrives.
PHP webhook signature verification in plain PHP and Laravel
Verify a Sume webhook in PHP: hash_hmac sha256 over timestamp.raw_body, split the sume-v1 entries, and compare each one with hash_equals.
Golang: verify a webhook signature with HMAC and hmac.Equal
Verify a Sume webhook in Go: read the body once with io.ReadAll, HMAC-SHA256 the timestamp and raw bytes, then hmac.Equal each sume-v1 entry.
Prompt injection and user input: pass data to an AI agent API
Put customer text in a Sume run's input object, not its instruction. The agent is told to read it as data; the docs call that a trust boundary, not a sandbox.
How to write a SKILL.md file for a Sume Format recipe
A Sume Format recipe is a SKILL.md file plus references. Keep SKILL.md a short index, move detail into references/, and follow the package rules.
How to verify an AI-generated video was delivered by a Sume run
Before you count a Sume run as delivered, check status and primary_output_url, read filled_by, and probe the file. Here is what Sume checks, and what it skips.
Optimistic concurrency with If-Match: edit Sume Format files by API
Edit a Sume Format's files over the API without overwriting another writer: each write carries the file's blob sha, and If-Match guards the whole package.
Share an AI video workflow with another team: Sume Format grants
Share a Sume team Format with another team workspace. Once the grant is live, that team calls the owner's address with its own team key and pays for its runs.
JSON Schema oneOf not supported in strict mode: fix the violations
Sume rejects an output_schema outside the OpenAI strict-mode subset with 400 output_schema_invalid. Read each violation's rule, then port oneOf and nullable.
Version control for AI agent prompts in production: Sume Formats
Every Sume Format edit bumps its version, and each run receipt records the version that ran. Runs cannot be pinned to a version, and there is no rollback API.
Which tool to generate UGC-style video ads for products at scale?
It depends on your input, presenter, languages, and volume. Arcads, Creatify, HeyGen, Runway, Synthesia, and Sume compared on API, pricing, and limits.
Prevent overlapping AI agent runs on Sume with on_active_run
Sume's on_active_run field decides what a second run request does while one is in flight: run anyway, record a skipped run, or get a 409 and nothing runs.
MCP server OAuth flow on Sume: discovery, consent, PKCE, and scopes
Sume's hosted MCP server runs its own OAuth: a 401 points to discovery metadata, the user consents on mcp.sume.com, and PKCE S256 yields a one-hour token.
MCP tool call timeouts on long-running video jobs: use jobs_wait
On Sume's hosted MCP server, one jobs_wait call holds at most 55 seconds. Wait out long video jobs in slices, batch up to 20 ids, and never resubmit.
Sume MCP tools list: hosted tools grouped by read, write, and paid
The Sume MCP tools list by family: which hosted tools only read, which write, which start paid jobs, and which tool names are not on hosted MCP at all.
Fix MCP insufficient_scope on Sume: scopes, missing tools, timeouts
An MCP insufficient_scope error on Sume means the OAuth session lacks mcp:write. Start with mcp_health, then fix scopes, missing tools, and timeouts.
Programmatic tool calling on MCP: how Sume's script_run works
script_run is programmatic tool calling on Sume's hosted MCP: a short JavaScript program calls tools in loops or in parallel under call and paid budgets.
Video editing MCP server: let an AI agent trim, filter, and assemble
Sume's hosted MCP server gives AI agents video editing tools: inspect, frames, trim, filter, audio detach, compose, and a Timeline render, each run as a job.
Sume agent run errors: action_run_in_progress, agent_run_not_found
409 action_run_in_progress means a schedule run is already active and you sent reject. 404 agent_run_not_found means the id is not your Agent Completion run.
How to run the Sume CLI in CI and on headless servers
Run the Sume CLI in CI with a pinned release binary, SUME_API_KEY from your secret store, an isolated SUME_CONFIG_DIR, a doctor preflight, and --json output.
Sume CLI commands: a reference for account, jobs, assets, and skills
The Sume CLI commands beyond generation: login and account, health and doctor checks, schema discovery, jobs, assets, batch helpers, skills, and aliases.
Sume CLI not working? Fixes for login, API base, jobs, and media
When the Sume CLI is not working, run four read-only checks, then fix the cause: a missing key, a wrong API base, an unfinished job, or a rejected media URL.
AI video generation API length limits: up to 30 seconds per clip
On Sume, seedance-2.5 (4–30 s) and wan-3.0 (2–30 s) make 30-second clips; other models stop at 15 s or less. Limits by model, the error, and going longer.
4K AI video generation API: resolutions by model, 360p to 4K
For 4K on Sume, pin gemini-omni-flash-1.1 with resolution 4K; minimax-h3 upscales to 2K or 4K. Resolutions for every video model, and the price effect.
Gemini Omni Flash 1.1 API: text, image, and reference video modes
Call Gemini Omni Flash 1.1 on Sume as gemini-omni-flash-1.1: text, image, or reference to video, 3–10 second clips from 360p to 4K, with native audio.
MiniMax H3 API: H3 and H3 Max video at native 768p with stereo audio
Call MiniMax H3 and H3 Max on Sume as minimax-h3 and minimax-h3-max: 5–15 second clips at native 480p or 768p, 1080p on H3 Max, always with stereo audio.
Lip sync API: turn an image and audio into a talking clip
Send a still image and Sume-hosted audio to VEED Fabric 1.0 or MiniMax H3 Max Lip Sync and get a talking clip back. Inputs, limits, and per-second pricing.
Image generation API models on Sume: edits, references, and masks
Sume's image generation API lists 17 models. See which edit from reference images, how many references each takes, which are text-only, and which take masks.